TimeCSL: Unsupervised Contrastive Learning of General Shapelets for Explorable Time Series Analysis
Zhiyu Liang, Chen Liang, Zheng Liang, Hongzhi Wang, Bo Zheng
TL;DR
TimeCSL tackles unsupervised, interpretable time series analysis under label scarcity by combining CSL with an end-to-end explorable pipeline. It introduces CSL as a contrastive-learning-based, shapelet-centric representation learner that produces $z_i=f(x_i)$ encoding (dis)similarity to learned shapelets across scales and metrics. TimeCSL unifies this representation with task-oriented analyzers and two operation modes—freezing and fine-tuning—along with a GUI for exploring raw series, shapelets, and the features. The demonstrated system yields strong downstream task performance and provides actionable insights, supporting semi-supervised settings and transparent decision reasoning.
Abstract
Unsupervised (a.k.a. Self-supervised) representation learning (URL) has emerged as a new paradigm for time series analysis, because it has the ability to learn generalizable time series representation beneficial for many downstream tasks without using labels that are usually difficult to obtain. Considering that existing approaches have limitations in the design of the representation encoder and the learning objective, we have proposed Contrastive Shapelet Learning (CSL), the first URL method that learns the general-purpose shapelet-based representation through unsupervised contrastive learning, and shown its superior performance in several analysis tasks, such as time series classification, clustering, and anomaly detection. In this paper, we develop TimeCSL, an end-to-end system that makes full use of the general and interpretable shapelets learned by CSL to achieve explorable time series analysis in a unified pipeline. We introduce the system components and demonstrate how users interact with TimeCSL to solve different analysis tasks in the unified pipeline, and gain insight into their time series by exploring the learned shapelets and representation.